© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13985
    Prev
    Next
    INDEX
    Explanations

    tail or tailings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -2.59
    <b>
    -2.03
    .’
    -1.99
     slight
    -1.79
    </sub>
    -1.76
     But
    -1.73
    ↵
    -1.72
    from
    -1.70
    ’.
    -1.68
    <i>
    -1.66
    POSITIVE LOGITS
    骉
    2.44
    𖧵
    2.33
     pomoci
    2.09
    
    2.06
     Evaluación
    2.05
     '
    2.03
    蛲
    2.00
     basé
    1.96
    tail
    1.95
    𓂀
    1.95
    Activations Density 0.006%

    No Known Activations